7th International Conference on Spoken Language Processing
September 16-20, 2002
Miniature Text to Speech (TTS) systems are broadly applied to embedded system and speech chip, where limited resource requires the corpus to be relatively small and the computing complexity to be low. In general, speech synthesized by conventional miniature TTS systems lacks naturalness due to the limitation of corpus size. In this paper, a method of automatic building a small corpus from a large speech database is described. A new way of distance measurement among candidate instances is also proposed. Based on the tailored corpus, a miniature Chinese TTS system is built, which can produce speech with high naturalness.
Bibliographic reference. Shuang, Zhi-Wei / Hu, Yu / Ling, Zhen-Hua / Wang, Ren-Hua (2002): "A miniature Chinese TTS system based on tailored corpus", In ICSLP-2002, 2389-2392.